Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    understanding of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shenanigans
    0.52
     문제를
    0.49
     ermög
    0.45
     شرطونو
    0.43
     проблемы
    0.43
    を使う
    0.43
     وړاند
    0.42
     problèmes
    0.42
     лечения
    0.42
     अजीब
    0.42
    POSITIVE LOGITS
     typically
    0.48
     typical
    0.45
    dasarkan
    0.44
    typically
    0.40
     usually
    0.40
     corresponding
    0.39
    the
    0.39
     generally
    0.39
    Typically
    0.39
     mostly
    0.38
    Act Density 0.124%

    No Known Activations